search

hengyuan-hu / bottom-up-attention-vqa

An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.
GNU General Public License v3.0
754 stars 181 forks source link

Using in python3 and PyTorch v0.4 #28

Closed zwx8981 closed 6 years ago

zwx8981 commented 6 years ago

Hi, thank you for your great work, I am just wondering is it possible to use it under environment of python3 and PyTorch v0.4?

hengyuan-hu commented 6 years ago

Thank you for your interest. You need to make some modifications to make the code work. Both python3 and pytorch 0.4 are not backward compatible. One issue I know is that in pytorch 0.4 weight norm is not working with parallel training due to a bug. On Tue, Jul 17, 2018 at 12:21 AM Onionbao notifications@github.com wrote:

Hi, thank you for your great work, I am just wondering is it possible to use it under environment of python3 and PyTorch v0.4?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/hengyuan-hu/bottom-up-attention-vqa/issues/28, or mute the thread https://github.com/notifications/unsubscribe-auth/AEglZYr9WyDk1HZ8R-QUuAyWGdv9d74Mks5uHZB7gaJpZM4VSUA4 .